Computer Science Theses and Dissertations

Permanent URI for this collectionhttp://hdl.handle.net/1903/2756

Browse

Subject: search.filters.subject.information retrieval

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Temporal Context Modeling for Text Streams
    (2018) Rao, Jinfeng; Lin, Jimmy; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    There is increasing recognition that time plays an essential role in many information seeking tasks. This dissertation explores temporal models on evolving streams of text and the role that such models play in improving information access. I consider two cases: a stream of social media posts by many users for tweet search and a stream of queries by an individual user for voice search. My work explores the relationship between temporal models and context models: for tweet search, the evolution of an event serves as the context of clustering relevant tweets; for voice search, the user's history of queries provides the context for helping understand her true information need. First, I tackle the tweet search problem by modeling the temporal contexts of the underlying collection. The intuition is that an information need in Twitter usually correlates with a breaking news event, thus tweets posted during that event are more likely to be relevant. I explore techniques to model two different types of temporal signals: pseudo trend and query trend. The pseudo trend is estimated through the distribution of timestamps from an initial list of retrieved documents given a query, which I model through continuous hidden Markov approach as well as neural network-based methods for relevance ranking and sequence modeling. As an alternative, the query trend, is directly estimated from the temporal statistics of query terms, obviating the need for an initial retrieval. I propose two different approaches to exploit query trends: a linear feature-based ranking model and a regression-based model that recover the distribution of relevant documents directly from query trends. Extensive experiments on standard Twitter collections demonstrate the superior effectivenesses of my proposed techniques. Second, I introduce the novel problem of voice search on an entertainment platform, where users interact with a voice-enabled remote controller through voice requests to search for TV programs. Such queries range from specific program navigation (i.e., watch a movie) to requests with vague intents and even queries that have nothing to do with watching TV. I present successively richer neural network architectures to tackle this challenge based on two key insights: The first is that session context can be exploited to disambiguate queries and recover from ASR errors, which I operationalize with hierarchical recurrent neural networks. The second insight is that query understanding requires evidence integration across multiple related tasks, which I identify as program prediction, intent classification, and query tagging. I present a novel multi-task neural architecture that jointly learns to accomplish all three tasks. The first model, already deployed in production, serves millions of queries daily with an improved customer experience. The multi-task learning model is evaluated on carefully-controlled laboratory experiments, which demonstrates further gains in effectiveness and increased system capabilities. This work now serves as the core technology in Comcast Xfinity X1 entertainment platform, which won an Emmy award in 2017 for the technical contribution in advancing television technologies. This dissertation presents families of techniques for modeling temporal information as contexts to assist applications with streaming inputs, such as tweet search and voice search. My models not only establish the state-of-the-art effectivenesses on many related tasks, but also reveal insights of how various temporal patterns could impact real information-seeking processes.
  • Thumbnail Image
    Item
    Searching to Translate and Translating to Search: When Information Retrieval Meets Machine Translation
    (2013) Ture, Ferhan; Lin, Jimmy; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    With the adoption of web services in daily life, people have access to tremendous amounts of information, beyond any human's reading and comprehension capabilities. As a result, search technologies have become a fundamental tool for accessing information. Furthermore, the web contains information in multiple languages, introducing another barrier between people and information. Therefore, search technologies need to handle content written in multiple languages, which requires techniques to account for the linguistic differences. Information Retrieval (IR) is the study of search techniques, in which the task is to find material relevant to a given information need. Cross-Language Information Retrieval (CLIR) is a special case of IR when the search takes place in a multi-lingual collection. Of course, it is not helpful to retrieve content in languages the user cannot understand. Machine Translation (MT) studies the translation of text from one language into another efficiently (within a reasonable amount of time) and effectively (fluent and retaining the original meaning), which helps people understand what is being written, regardless of the source language. Putting these together, we observe that search and translation technologies are part of an important user application, calling for a better integration of search (IR) and translation (MT), since these two technologies need to work together to produce high-quality output. In this dissertation, the main goal is to build better connections between IR and MT, for which we present solutions to two problems: Searching to translate explores approximate search techniques for extracting bilingual data from multilingual Wikipedia collections to train better translation models. Translating to search explores the integration of a modern statistical MT system into the cross-language search processes. In both cases, our best-performing approach yielded improvements over strong baselines for a variety of language pairs. Finally, we propose a general architecture, in which various components of IR and MT systems can be connected together into a feedback loop, with potential improvements to both search and translation tasks. We hope that the ideas presented in this dissertation will spur more interest in the integration of search and translation technologies.
  • Thumbnail Image
    Item
    Combining Evidence from Unconstrained Spoken Term Frequency Estimation for Improved Speech Retrieval
    (2008-11-21) Olsson, James Scott; Oard, Douglas W; Applied Mathematics and Scientific Computation; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This dissertation considers the problem of information retrieval in speech. Today's speech retrieval systems generally use a large vocabulary continuous speech recognition system to first hypothesize the words which were spoken. Because these systems have a predefined lexicon, words which fall outside of the lexicon can significantly reduce search quality---as measured by Mean Average Precision (MAP). This is particularly important because these Out-Of-Vocabulary (OOV) words are often rare and therefore good discriminators for topically relevant speech segments. The focus of this dissertation is on handling these out-of-vocabulary query words. The approach is to combine results from a word-based speech retrieval system with those from vocabulary-independent ranked utterance retrieval. The goal of ranked utterance retrieval is to rank speech utterances by the system's confidence that they contain a particular spoken word, which is accomplished by ranking the utterances by the estimated frequency of the word in the utterance. Several new approaches for estimating this frequency are considered, which are motivated by the disparity between reference and errorfully hypothesized phoneme sequences. The first method learns alternate pronunciations or degradations from actual recognition hypotheses and incorporates these variants into a new generative estimator for term frequency. A second method learns transformations of several easily computed features in a discriminative model for the same task. Both methods significantly improved ranked utterance retrieval in an experimental validation on new speech. The best of these ranked utterance retrieval methods is then combined with a word-based speech retrieval system. The combination approach uses a normalization learned in an additive model, which maps the retrieval status values from each system into estimated probabilities of relevance that are easily combined. Using this combination, much of the MAP lost because of OOV words is recovered. Evaluated on a collection of spontaneous, conversational speech, the system recovers 57.5\% of the MAP lost on short (title-only) queries and 41.3\% on longer (title plus description) queries.
  • Thumbnail Image
    Item
    Supporting Exploratory Web Search With Meaningful and Stable Categorized Overviews
    (2006-04-28) Kules, Bill; Shneiderman, Ben; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This dissertation investigates the use of categorized overviews of web search results, based on meaningful and stable categories, to support exploratory search. When searching in digital libraries and on the Web, users are challenged by the lack of effective overviews. Adding categorized overviews to search results can provide substantial benefits when searchers need to explore, understand, and assess their results. When information needs are evolving or imprecise, categorized overviews can stimulate relevant ideas, provoke illuminating questions, and guide searchers to useful information they might not otherwise find. When searchers need to gather information from multiple perspectives or sources, categorized overviews can make those aspects visible for interactive filtering and exploration. However, they add visual complexity to the interface and increase the number of tactical decisions to be made while examining search results. Two formative studies (N=18 and N=12) investigated how searchers use categorized overviews in the domain of U.S. government web search. A third study (N=24) evaluated categorized overviews of general web search results based on thematic, geographic, and government categories. Participants conducted four exploratory searches during a two hour session to generate ideas for newspaper articles about specified topics. Results confirmed positive findings from the formative studies, showing that subjects explored deeper while feeling more organized and satisfied, but did not find objective differences in the outcomes of the search task. Results indicated that searchers use categorized overviews based on thematic, geographic, and organizational categories to guide the next steps in their searches. This dissertation identifies lightweight search actions and tactics made possible by adding a categorized overview to a list of web search results. It describes a design space for categorized overviews of search results, and presents a novel application of the brushing and linking technique to enrich search result interfaces with lightweight interactions. It proposes a set of principles, refined by the studies, for the design of exploratory search interfaces, including "Organize overviews around meaningful categories," "Clarify and visualize category structure," and "Tightly couple category labels to search result list." These contributions will be useful to web search researchers and designers, information architects and web developers.